Member of Technical Staff (AI Supportability)

Category-defining tech. Career-defining work. Lots of tech companies disrupt. But, many fail when they try to scale. We're different. CockroachDB makes it easier for companies to build and scale apps. This is how and why we're helping some of the most innovative companies on the planet. We tackle problems head-on and focus on solutions that create lasting impact.  Because when our customers win, we all win.    The Role Can LLMs accurately diagnose complex database issues from telemetry data? We're building a team to prove this. Supporting CockroachDB is inherently challenging. Our product has thousands of unique metrics, complex structured data, and emits detailed logs at high frequency, making support tickets expensive and time-consuming to resolve. We're launching an R&D initiative to explore how Applied AI can reduce these support costs and improve diagnostic accuracy. We're looking for engineers who thrive in exploratory, prototype-driven environments working closely with end users. You'll start with a concrete mission: validate whether LLMs can perform root cause analysis on real Zendesk escalations using CockroachDB telemetry data. Working embedded with our technical support engineers, you'll experiment with OpenAI/Anthropic APIs, prompt engineering techniques, and various data contexts to determine if AI can transform diagnostic workflows. This isn't about executing a predetermined roadmap. It's about rapid experimentation, learning from real data, and building the foundation for AI-powered support workflows. If you're energized by building from scratch, working directly with internal stakeholders, and technical challenges where the outcome isn't guaranteed, this role is for you. You Will Start with focused validation : Design experiments to test whether LLMs can assist with root cause analysis on real Zendesk escalations, determining if AI can accelerate diagnostic workflows and reduce time-to-resolution. Work embedded with our Bangalore technical support team:  Partner with support engineers through regular collaboration sessions to understand diagnostic workflows, review experimental results, and gather insights. Work with real CockroachDB data : Process diagnostic telemetry including cluster metrics, SQL traces, system logs, plus observability data. Iterate on AI approaches : Experiment with OpenAI/Anthropic APIs, prompt engineering techniques, and different data contexts to optimize LLM diagnostic performance. Build rapid prototypes : Transform promising validation results into proof-of-concept tools and agents, defining next steps based on what the data tells us. Measure and document progress : Establish clear success metrics for LLM accuracy and track experimental results throughout the validation process. Scale successful experiments : Use Go, Python, and cloud infrastructure to build scalable applications from validated prototype. Explore advanced AI patterns : As validation results warrant, investigate sophisticated approaches like agentic workflows, MCP integrations, and multi-step reasoning chains for complex diagnostic scenarios The Expectations In the first month, you will join the AI Supportability team and immerse yourself in CockroachDB's observability landscape and support workflows. Embed with technical support engineers to understand diagnostic challenges firsthand while beginning LLM experimentation for supportability use cases. After 3 months, you'll have validated core assumptions about LLM-powered diagnostics and be actively prototyping the next-generation of AI support tools. You will have established strong collaborative relationships with technical support teams and identified the most promising areas for AI automation based on real experimental data. As this initiative grows, you will have the opportunity to define the future of AI-driven customer support at Cockroach Labs. Your Applied AI work will establish whether and how AI can scale our support organization, potentially influencing product development for improved customer self-service. This initiative will determine our long-term AI supportability strategy. You Have Experimental mindset : You're energized by ambiguous problems, rapid prototyping, and discovering solutions through data-driven experimentation Applied AI/ML work : Experience with LLMs, prompt engineering, and model evaluation through professional work, significant side projects, or deep technical exploration Strong programming skills : Proficiency in Go, Python or similar languages, with ability to quickly learn new technologies and APIs Data and systems experience : Comfort working with large-scale structured data, APIs, observability tools, logs, metrics, and distributed systems concepts Greenfield experience : Background building new products, prototypes, or research projects where the solution path wasn't predefined Embedded collaboration experience : Experience working directly with internal stakeholders,